Accumulated snow cleaning method, device and equipment based on municipal road and readable medium

Abstract

The embodiment of the invention discloses an accumulated snow cleaning method, device and equipment based on municipal roads and a readable medium. A specific embodiment of the method comprises the following steps: acquiring an environment information set and a road information set; determining a road cleaning priority of each road corresponding to the road information set, and generating a road sequence according to each determined road cleaning priority; executing the following processing steps: based on the environment information and the road information corresponding to the road, executing a memory network prediction operation to generate predicted environment information and road information as the environment information and the road information corresponding to the road; inputting the environment information and the road information corresponding to the road into a pre-trained resource scheduling model; and based on the determined priority of each road and each resource scheduling result, controlling an associated cleaning vehicle to execute an accumulated snow cleaning task. According to the embodiment, the conditions of traffic jam and waste of cleaning resources are avoided.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, apparatus, device, and readable medium for clearing snow on municipal roads. Background Art

[0002] When snowfall is heavy, snow often accumulates on municipal roads, affecting normal traffic. Therefore, snowplows are needed to clear the snow from these roads. Currently, a common method for clearing snow is to allocate a quota of snowplows and snowmelt to each municipal road to perform the snow clearing task.

[0003] However, when using the above method to clear snow, the following technical problems often occur:

[0004] Different roads have different amounts of snow, importance, and traffic volumes. When a quota of snowplows and snowmelt is allocated to different roads, snow may not be cleared in a timely manner, leading to traffic jams and waste of clearing resources.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure provide a method, device, electronic device, and computer-readable medium for clearing snow on municipal roads to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a snow clearing method based on municipal roads, the method comprising: obtaining an environmental information set and a road information set, wherein the environmental information in the environmental information set comprises: snowfall, temperature and wind speed, and the road information in the road information set comprises road status information, and the road status information comprises road surface temperature, snow thickness and ice degree; determining the road clearing priority of each road corresponding to the road information set, and generating a road sequence according to the determined road clearing priority; for each road in the road sequence, performing the following processing steps: based on the environmental information and road information corresponding to the road, performing a memory network prediction operation to generate predicted environmental information and road information as the environmental information and road information corresponding to the road; inputting the environmental information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result; and based on the determined road priorities and resource scheduling results, controlling the associated clearing vehicles to perform snow clearing tasks.

[0009] In a second aspect, some embodiments of the present disclosure provide a snow clearing device based on municipal roads, the device comprising: an acquisition unit configured to acquire an environmental information set and a road information set, wherein the environmental information in the environmental information set comprises: snowfall, temperature and wind speed, and the road information in the road information set comprises road status information, and the road status information comprises road surface temperature, snow thickness and ice degree; a determination unit configured to determine the road clearing priority of each road corresponding to the road information set, and generate a road sequence according to the determined road clearing priority; an execution unit configured to perform the following processing steps for each road in the road sequence: based on the environmental information and road information corresponding to the road, perform a memory network prediction operation to generate predicted environmental information and road information as the environmental information and road information corresponding to the road; input the environmental information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result; a control unit configured to control the associated clearing vehicle to perform the snow clearing task based on the determined road priorities and resource scheduling results.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0012] The above-described embodiments of the present disclosure have the following beneficial effects: The municipal road snow-clearing methods of some embodiments of the present disclosure avoid traffic jams and waste of clearing resources. Specifically, traffic jams and waste of clearing resources arise from the fact that different roads have varying amounts of snow, importance, and traffic volume. When a quota of snowplows and snowmelt is allocated to different roads, snow may not be cleared in a timely manner, leading to traffic jams and waste of clearing resources. Based on this, the municipal road snow-clearing methods of some embodiments of the present disclosure first obtain an environmental information set and a road information set. This allows the current environmental information and road conditions to be determined. Second, a road clearing priority is determined for each road corresponding to the road information set, and a road sequence is generated based on the determined road clearing priorities. This allows the road priorities of different roads to be determined and sorted. Then, for each road in the road sequence, the following processing steps are performed: First, a memory network prediction operation is performed based on the environmental information and road information corresponding to the road to generate predicted environmental information and road information as the environmental information and road information corresponding to the road. This avoids the situation where data is missing and cleaning resource scheduling cannot be performed. Second, the environmental information and road information corresponding to the above-mentioned roads are input into the pre-trained resource scheduling model to obtain the resource scheduling results. This allows the cleaning resources required for the road to be determined. Finally, based on the determined priorities of each road and the resource scheduling results, the associated cleaning vehicles are controlled to perform snow clearing tasks. In this way, snow clearing tasks can be performed on each road. Because cleaning resources are allocated based on road priorities and the degree of snow accumulation on the road, cleaning resources are rationally planned, thereby avoiding the situation of untimely snow clearing, traffic jams, and waste of cleaning resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of a snow clearing method based on municipal roads according to the present disclosure;

[0015] Figure 2 1 is a schematic structural diagram of some embodiments of a snow clearing device for municipal roads according to the present disclosure;

[0016] Figure 3is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0019] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0020] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0021] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0022] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0023] Figure 1 The process 100 of some embodiments of the method for clearing snow from municipal roads according to the present disclosure is shown. The method for clearing snow from municipal roads comprises the following steps:

[0024] Step 101: Acquire an environment information set and a road information set.

[0025] In some embodiments, an entity executing a snow-clearing method for municipal roads (e.g., a server) may obtain an environmental information set and a road information set. The environmental information in the environmental information set may include snowfall, temperature, and wind speed. The road information in the road information set may include road status information, including road surface temperature, snow thickness, and ice level.

[0026] Optionally, the above-mentioned environment information set and the above-mentioned road information set may be obtained through the following steps:

[0027] The first step is to obtain the terminal interface corresponding to the meteorological service terminal.

[0028] In some embodiments, the execution entity may obtain a terminal interface corresponding to a meteorological service terminal, which may be a meteorological service terminal of a meteorological bureau. The terminal interface may be an interface for obtaining environmental information.

[0029] In the second step, based on the terminal interface, at least one piece of environmental information corresponding to the meteorological service terminal is obtained as an environmental information set.

[0030] In some embodiments, the execution entity may obtain at least one piece of environmental information corresponding to the weather service terminal based on the terminal interface as an environmental information set.

[0031] In the third step, for each road, perform the following collection steps:

[0032] In the first collection step, at least one initial road information is obtained based on the information collection device group to obtain an initial road information set.

[0033] In some embodiments, the execution entity may obtain at least one piece of initial road information based on a group of information collection devices to obtain an initial road information set. The information collection devices in the group may be environmental information collection devices pre-deployed on various roads. These environmental information collection devices may be cameras or sensors. For example, these environmental information collection devices may be embedded temperature sensors. The initial road information may represent the ambient temperature, snow depth, and ice level of the road.

[0034] In the second collection step, each piece of initial road information in the initial road information set is preprocessed to generate preprocessed pieces of initial road information as road information.

[0035] In some embodiments, the execution entity may pre-process each piece of initial road information in the initial road information set to generate pre-processed pieces of initial road information as the road information, wherein the pre-processing may be a normalization process.

[0036] Step 102 : determining a road clearing priority for each road corresponding to the road information set, and generating a road sequence according to the determined road clearing priority.

[0037] In some embodiments, the execution entity may determine a road cleaning priority for each road corresponding to the road information set, and generate a road sequence based on the determined road cleaning priorities. The road cleaning priorities may represent the order in which cleaning tasks are executed on the roads.

[0038] In practice, road clearing priorities can be determined by the following steps:

[0039] The first step is to obtain the road operation information of each road in the road information set to obtain the road operation information set. The road operation information includes: road grade, real-time traffic flow and emergency attributes.

[0040] The second step is to determine the road clearing priority corresponding to each of the above roads based on a preset priority algorithm and the above road operation information set.

[0041] In the process of adopting technical solutions to solve the technical problems mentioned in the background technology, the following technical problems are often accompanied: when clearing roads, due to limited clearing resources, the clearing priority of the roads is not set, which leads to the inability to clear important roads in time during road clearing, resulting in road vehicle congestion and waste of cleaning resources. Here, the conventional solution is generally to use the traffic volume of the road as the evaluation standard of the importance of the road, sort the roads, and clear the roads. However, the above conventional solution still has the following problems: the traffic volume of the road cannot be used as the only criterion for judging the importance of the road. Using the traffic volume of the road as the evaluation standard of the importance of the road alone leads to untimely clearing of snow on the road, which takes a long time to clear the snow on the road and causes vehicle congestion on the road.

[0042] Here, the road clearing priority corresponding to each of the above roads can be determined through the following sub-steps:

[0043] The first sub-step is to construct a dynamic judgment matrix for cleaning priorities based on road grade, real-time traffic volume, and emergency attributes. The dynamic judgment matrix for cleaning priorities can include three dynamic weights and three static weights. The static weights can be pre-set weights. In practice, the dynamic judgment matrix can be expressed as follows:

[0044] a_ij=(C i / C j ) β *(V i / V j ) λ *(E i / E j ) γ .

[0045] Among them, the above β, λ, and γ are pre-set static weights. As an example, the above β can be 0.4, which is used to characterize the road grade weight, the above λ can be 0.3, which is used to characterize the road traffic flow weight, and the above γ can be 0.3, which is used to characterize the emergency attribute weight. C represents the road grade, V represents the real-time traffic flow, and E represents the emergency attribute. i / C j 、V i / V j and E i / E j It can be a pre-set dynamic weight. i represents the current time point. j represents a historical time point before the current time point that is separated from the current time point by a preset time length. The above preset time length can be 30 minutes.

[0046] In the second sub-step, the road operation information in the above road operation information set, including the road grade, real-time traffic flow and emergency attributes, is input into the above cleaning priority dynamic judgment matrix to determine the weight values ​​of the grade dynamic weight, traffic flow dynamic weight and emergency attribute dynamic weight.

[0047] The third sub-step is to generate a road clearing priority based on the above-mentioned dynamic weight of the level, the above-mentioned dynamic weight of the traffic flow, and the above-mentioned dynamic weight of the emergency attribute.

[0048] Optionally, after the third sub-step, the method further includes the following steps:

[0049] The fourth sub-step is to determine the road grade, real-time traffic volume, emergency attributes and historical weight performance of the above-mentioned road operation information as an updated state in response to the current time being the preset update time.

[0050] The fifth sub-step is to perform a preset action based on the updated state, wherein the preset action may be to adjust the three static weights according to the corresponding adjustment intervals.

[0051] The sixth sub-step is generating a predicted reward based on the preset action. The predicted reward includes positive and negative rewards. Positive rewards can include reduced road congestion and shorter emergency response times due to the determined priority. Negative rewards can include increased road congestion due to weight adjustment.

[0052] In practice, prediction rewards can be generated by following these steps:

[0053] The first generation step is to perform feature importance evaluation on the road grade, real-time traffic flow and emergency attribute of the road operation information in the road operation information set to generate a road grade contribution, a traffic flow contribution and an emergency attribute contribution;

[0054] The second generation step is to monitor in real time whether abnormal events occur on each road corresponding to the road operation information set. The abnormal events may be events that hinder the normal passage of vehicles on the road. As an example, the abnormal events may be traffic accidents or road maintenance.

[0055] The third generating step is to classify the abnormal event in response to monitoring the occurrence of the abnormal event on the target road to generate classification information. The classification processing can be to classify the level of the abnormal event to generate classification information.

[0056] The fourth generation step is to query a preset variation table based on the classification information to determine a contribution variation group corresponding to the abnormal event. The preset variation table may be a pre-set table of contribution variation corresponding to different levels of abnormal events.

[0057] The fifth generation step comprises obtaining a congestion index corresponding to the target road, and dynamically correcting each contribution change in the contribution change group using the congestion index to obtain a corrected contribution change group. The congestion index can be obtained in real time via an associated road condition interface.

[0058] The sixth generation step is to update the road grade contribution, the traffic flow contribution and the emergency attribute contribution based on the modified contribution change group.

[0059] The seventh generating step generates a first predicted reward based on the road operation information in the road operation information set, including road grade, real-time traffic flow, and emergency attributes. In practice, the first predicted reward can be determined as the sum of the product of the road grade and the revised road grade contribution, the product of the real-time traffic flow and the revised traffic flow contribution, and the product of the emergency attribute and the emergency attribute contribution.

[0060] The eighth generation step is to generate a second prediction reward based on the classification information, wherein the second prediction reward may be the product of 0.2 and the classification information.

[0061] The ninth generation step comprises generating a reward constraint value corresponding to the target road, and generating a predicted reward based on the first predicted reward, the second predicted reward, and the reward constraint value. The reward constraint value may be the product of the number of abnormal events that occurred on the target road within a preset historical time period and 1%. The predicted reward may be the difference between the sum of the first predicted reward and the second predicted reward and the reward constraint value.

[0062] In the seventh sub-step, based on the predicted rewards, the three static weights are updated. Here, the weight policy network can be updated using Q-learning or PPO algorithms.

[0063] In the eighth sub-step, the three static weights are normalized and subjected to boundary constraints to generate three normalized static weights.

[0064] The first through sixth sub-steps described above, as an inventive feature of an embodiment of the present disclosure, in conjunction with step 104 below, address the technical problem of "due to limited cleaning resources, a lack of clearing priorities for roads during road clearing, resulting in the inability to clear important roads in a timely manner, causing traffic congestion and a waste of clearing resources." The reasons for this traffic congestion and waste of clearing resources are as follows: due to limited cleaning resources, a lack of clearing priorities for roads during road clearing, resulting in the inability to clear important roads in a timely manner, causing traffic congestion and a waste of clearing resources. Resolving these factors can reduce the time required to search for geographic entities. To achieve this, the present disclosure first constructs a dynamic judgment matrix; the road operation information in the road operation information set, including road grade, real-time traffic volume, and emergency attributes, is input into the dynamic judgment matrix to generate a first dynamic weight, a second dynamic weight, and a third dynamic weight. Thus, the three dynamic weights can be used to determine the road clearing priorities for different roads, enabling timely snow clearing of important roads and avoiding traffic congestion. Second, based on the first, second, and third dynamic weights, a road clearing priority is generated. This allows the priority of different roads to be determined. Third, in response to the current time being a preset update time, the road operation information, including road grade, real-time traffic volume, emergency attributes, and historical weight performance, is determined to be in an updated state. This allows real-time road status to be obtained. Fourth, based on the updated state, a preset action is executed; a predicted reward is generated based on the preset action; and based on the predicted reward, the three static weights are updated. This allows the weights to be updated based on the real-time road status, and thus the road priorities to be updated in real time. This allows for timely snow clearing of roads based on the dynamic priorities, further avoiding road congestion and waste of clearing resources due to unupdated priorities. Fifth, the three static weights are normalized and bounded to generate three normalized static weights. In conjunction with step 104, the associated clearing vehicles are controlled to perform snow clearing tasks based on the determined road priorities and resource scheduling results. In this way, snow can be cleared from roads based on dynamically generated road priorities, thus avoiding waste of clearing resources and avoiding traffic congestion on roads.

[0065] Step 103: For each road in the road sequence, perform the following processing steps:

[0066] Step 1031 : Based on the environment information and road information corresponding to the road, a memory network prediction operation is performed to generate predicted environment information and road information as the environment information and road information corresponding to the road.

[0067] In some embodiments, the execution entity may perform a memory network prediction operation based on the environmental information and road information corresponding to the road to generate predicted environmental information and road information as the environmental information and road information corresponding to the road.

[0068] Step 1032: Input the environmental information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result.

[0069] In some embodiments, the execution entity may input the environmental information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result. Here, the resource scheduling model may be a pre-trained hybrid regression model. Here, the training samples of the resource scheduling model may include: environmental information and road information of the road, as well as the number of snowplows and the amount of snowmelt used corresponding to the environmental information and road information. The resource scheduling model may include a first sub-model and a second sub-model. The first sub-model may be an XGBoost regression tree model. The second sub-model may be an LSTM model.

[0070] In practice, the resource scheduling model can be trained by the following steps:

[0071] The first step is to obtain a preset number of historical resource scheduling information groups. The preset number of historical resource scheduling information groups includes abnormal snowfall cases. The preset number can be a pre-set number of historical resource scheduling information groups. For example, the preset number can be 1000.

[0072] In the second step, based on the temperature gradient, a cubic spline interpolation process is performed to perform the model training step.

[0073] The third step is to verify the model results through a spatiotemporal cross-validation method using a validation group including the preset number of historical resource scheduling information groups. Here, the validation can be terminated in response to no improvement in the validation loss for 10 consecutive rounds.

[0074] Step 104 : Based on the determined priorities of the roads and the resource scheduling results, the associated snow clearing vehicles are controlled to perform the snow clearing task.

[0075] In some embodiments, the execution entity may control associated snow clearing vehicles to perform snow clearing tasks based on the determined road priorities and resource scheduling results. The associated snow clearing vehicles may be vehicles with snow clearing capabilities. For example, the snow clearing vehicles may be unmanned snow plows.

[0076] Optionally, after step 104, the following steps are further included:

[0077] In the first step, for each road in the above road sequence, the following collection steps are performed:

[0078] The first acquisition step is to acquire the vehicle trajectory of the cleaning vehicle corresponding to the above-mentioned road based on the target shooting device.

[0079] In some embodiments, the execution entity may collect the vehicle trajectory of the cleaning vehicle corresponding to the road based on a target shooting device.

[0080] In the second collection step, the snow thickness corresponding to the above-mentioned road is determined in real time through the target sensor.

[0081] In some embodiments, the execution entity may determine the thickness of snow corresponding to the road in real time through a target sensor.

[0082] In the third collection step, the above-mentioned vehicle trajectory and the real-time determined snow thickness are input into a pre-trained clearing progress prediction model to generate a clearing progress prediction result.

[0083] In some embodiments, the execution entity may input the vehicle trajectory and the real-time snow thickness into a pre-trained clearing progress prediction model to generate a clearing progress prediction result. The clearing progress prediction model may include a first feature extraction layer, a second feature extraction layer, a feature fusion layer, an attention mechanism layer, and an output layer.

[0084] In practice, the above-mentioned vehicle trajectories and the real-time snow thickness are input into a pre-trained clearing progress prediction model to generate a clearing progress prediction result, which may include the following sub-steps:

[0085] In the first sub-step, the vehicle trajectory is input into the first feature extraction layer to obtain trajectory time series features, wherein the trajectory time series features include: movement speed and turning frequency.

[0086] In the second sub-step, the snow thickness is input into the second feature extraction layer to obtain spatial features corresponding to the snow thickness, wherein the spatial features include snow gradient.

[0087] In the third sub-step, the trajectory temporal features and the spatial features are flattened to generate flattened temporal features and flattened spatial features.

[0088] In the fourth sub-step, based on the feature fusion layer, the flattened temporal features and the flattened spatial features are fused to generate fused features.

[0089] In the fifth sub-step, the fused features are input into the attention mechanism layer to generate a weighted spatial feature map.

[0090] The sixth sub-step is to input the weighted spatial feature map into the fully connected layer to integrate the features represented by the formaldehyde post-spatial feature map to generate global features.

[0091] The seventh sub-step is to map the above global features into the target regression space.

[0092] In the eighth sub-step, a regression operation is performed based on the global features in the target regression space, and the cleaning progress prediction result is output through the above-mentioned output layer.

[0093] In the second step, each generated cleaning progress prediction is sent to the target terminal for display.

[0094] In some embodiments, the execution entity may send the generated cleaning progress predictions to a target terminal for display.

[0095] The above-described embodiments of the present disclosure have the following beneficial effects: The municipal road snow-clearing methods of some embodiments of the present disclosure avoid traffic jams and waste of clearing resources. Specifically, traffic jams and waste of clearing resources arise from the fact that different roads have varying amounts of snow, importance, and traffic volume. When a quota of snowplows and snowmelt is allocated to different roads, snow may not be cleared in a timely manner, leading to traffic jams and waste of clearing resources. Based on this, the municipal road snow-clearing methods of some embodiments of the present disclosure first obtain an environmental information set and a road information set. This allows the current environmental information and road conditions to be determined. Second, a road clearing priority is determined for each road corresponding to the road information set, and a road sequence is generated based on the determined road clearing priorities. This allows the road priorities of different roads to be determined and sorted. Then, for each road in the road sequence, the following processing steps are performed: First, a memory network prediction operation is performed based on the environmental information and road information corresponding to the road to generate predicted environmental information and road information as the environmental information and road information corresponding to the road. This avoids the situation where data is missing and cleaning resource scheduling cannot be performed. Second, the environmental information and road information corresponding to the above-mentioned roads are input into the pre-trained resource scheduling model to obtain the resource scheduling results. This allows the cleaning resources required for the road to be determined. Finally, based on the determined priorities of each road and the resource scheduling results, the associated cleaning vehicles are controlled to perform snow clearing tasks. In this way, snow clearing tasks can be performed on each road. Because cleaning resources are allocated based on road priorities and the degree of snow accumulation on the road, cleaning resources are rationally planned, thereby avoiding the situation of untimely snow clearing, traffic jams, and waste of cleaning resources.

[0096] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a snow clearing device for municipal roads. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the municipal road snow clearing device can be specifically applied to various electronic devices.

[0097] like Figure 2As shown, a snow clearing device 200 for municipal roads in some embodiments includes: an acquisition unit 201 , a determination unit 202 , an execution unit 203 and a control unit 204 . Among them, the acquisition unit 201 is configured to acquire an environmental information set and a road information set, wherein the environmental information in the above-mentioned environmental information set includes: snowfall, temperature and wind speed, and the road information in the above-mentioned road information set includes road status information, and the above-mentioned road status information includes road surface temperature, snow thickness and ice degree; the determination unit 202 is configured to determine the road clearing priority of each road corresponding to the above-mentioned road information set, and generate a road sequence according to the determined road clearing priority; the execution unit 203 is configured to perform the following processing steps for each road in the above-mentioned road sequence: based on the environmental information and road information corresponding to the above-mentioned road, perform a memory network prediction operation to generate predicted environmental information and road information as the environmental information and road information corresponding to the above-mentioned road; input the environmental information and road information corresponding to the above-mentioned road into a pre-trained resource scheduling model to obtain a resource scheduling result; the control unit 204 is configured to control the associated clearing vehicle to perform the snow clearing task based on the determined road priorities and resource scheduling results.

[0098] It is understood that the units described in the municipal road snow clearing device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the snow clearing device 200 for municipal roads and the units included therein, and will not be described in detail here.

[0099] Reference below Figure 3 , which shows a schematic structural diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. The electronic devices in some embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0100] like Figure 3As shown, the electronic device 300 may include a processing device 301 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. Various programs and data required for the operation of the electronic device 300 are also stored in the RAM 303. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0101] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0102] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0103] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0104] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0105] The computer-readable medium may be included in the electronic device or may exist separately and not incorporated into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: obtain an environmental information set and a road information set, wherein the environmental information in the environmental information set includes snowfall, temperature, and wind speed; and the road information in the road information set includes road state information, including road surface temperature, snow depth, and ice level; determine a road clearing priority for each road in the road information set, and generate a road sequence based on the determined road clearing priorities. For each road in the road sequence, the following processing steps are performed: based on the environmental information and road information corresponding to the road, a memory network prediction operation is performed to generate predicted environmental information and road information as the environmental information and road information corresponding to the road; the environmental information and road information corresponding to the road are input into a pre-trained resource scheduling model to obtain a resource scheduling result; and based on the determined road priorities and resource scheduling results, the associated snow clearing vehicle is controlled to perform a snow clearing task.

[0106] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The units described in some embodiments of the present disclosure may be implemented in software or hardware. The units described may also be provided in a processor. For example, they may be described as follows: a processor includes an acquisition unit, a determination unit, an execution unit, and a control unit. The names of these units do not, in some cases, limit the units themselves. For example, the acquisition unit may also be described as a "unit for acquiring an environmental information set and a road information set."

[0109] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0110] The above description is only an illustration of some preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for clearing snow on municipal roads, comprising: Acquire an environmental information set and a road information set, wherein the environmental information in the environmental information set includes: snowfall, temperature, and wind speed; the road information in the road information set includes road state information, and the road state information includes road surface temperature, snow thickness, and ice degree; determining a road clearing priority for each road corresponding to the road information set, and generating a road sequence according to the determined road clearing priority; For each road in the road sequence, the following processing steps are performed: performing a memory network prediction operation based on the environment information and road information corresponding to the road to generate predicted environment information and road information as the environment information and road information corresponding to the road; Inputting the environmental information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result; Based on the determined road priorities and resource scheduling results, the associated snow clearing vehicles are controlled to perform snow clearing tasks.

2. The method according to claim 1, wherein The environment information set and the road information set are obtained by the following steps: Get the terminal interface corresponding to the meteorological service terminal; Based on the terminal interface, obtaining at least one piece of environmental information corresponding to the meteorological service terminal as an environmental information set; For each road, perform the following collection steps: Based on the information collection device group, obtaining at least one initial road information to obtain an initial road information set; Each piece of initial road information in the initial road information set is preprocessed to generate preprocessed pieces of initial road information as road information.

3. The method according to claim 1, wherein The determining of the road clearing priority of each road corresponding to the road information set includes: Acquiring road operation information of each road in each road corresponding to the road information set to obtain a road operation information set, wherein the road operation information includes: road grade, real-time traffic flow, and emergency attributes; Based on a preset priority algorithm and the road operation information set, a road clearing priority corresponding to each of the roads is determined.

4. The method according to claim 1, wherein The method further comprises: For each road in the road sequence, the following acquisition steps are performed: Based on the target shooting device, a vehicle trajectory of the cleaning vehicle corresponding to the road is collected; Determine the snow thickness corresponding to the road in real time through a target sensor; Inputting the vehicle trajectory and the real-time determined snow thickness into a pre-trained clearing progress prediction model to generate a clearing progress prediction result; The generated cleaning progress predictions are sent to the target terminal for display.

5. The method according to claim 4, wherein The cleaning progress prediction model includes: a first feature extraction layer, a second feature extraction layer, a feature fusion layer, an attention mechanism layer, a fully connected layer and an output layer; and The step of inputting the vehicle trajectory and the real-time determined snow thickness into a pre-trained clearing progress prediction model to generate a clearing progress prediction result includes: Inputting the vehicle trajectory into the first feature extraction layer to obtain trajectory time series features, wherein the trajectory time series features include: moving speed and turning frequency; Inputting the snow thickness into the second feature extraction layer to obtain spatial features corresponding to the snow thickness, wherein the spatial features include: snow gradient; Flattening the trajectory temporal features and the spatial features respectively to generate flattened temporal features and flattened spatial features; Based on the feature fusion layer, the flattened temporal features and the flattened spatial features are fused to generate fused features; Inputting the fused features into the attention mechanism layer to generate a weighted spatial feature map; Inputting the weighted post-spatial feature map into the fully connected layer to integrate the features represented by the formaldehyde post-spatial feature map to generate a global feature; Mapping the global features into the target regression space; Based on the global features in the target regression space, a regression operation is performed, and a cleaning progress prediction result is output through the output layer.

6. A snow clearing device for municipal roads, comprising: an acquisition unit configured to acquire an environmental information set and a road information set, wherein the environmental information in the environmental information set includes snowfall, temperature, and wind speed, and the road information in the road information set includes road state information, and the road state information includes road surface temperature, snow thickness, and ice degree; a determining unit configured to determine a road clearing priority of each road corresponding to the road information set, and generate a road sequence according to the determined road clearing priority; An execution unit is configured to perform the following processing steps for each road in the road sequence: performing a memory network prediction operation based on the environment information and road information corresponding to the road to generate predicted environment information and road information as the environment information and road information corresponding to the road; and inputting the environment information and road information corresponding to the road into a pre-trained resource scheduling model to obtain a resource scheduling result; The control unit is configured to control the associated snow clearing vehicles to perform snow clearing tasks based on the determined road priorities and resource scheduling results.

7. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images